Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/s977043/PlanGateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/s977043/plangate/retrospective-analyst)<a href="https://agentmods.dev/agents/s977043/plangate/retrospective-analyst"><img src="https://agentmods.dev/badge/agents/s977043/plangate/retrospective-analyst.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01192 |
| Opus 5 | $0.00032 | $0.00596 |
| Sonnet 5 | $0.00013 | $0.00238 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
retrospective-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective Analyst — Post-Exec Improvement Agent
プロジェクト共通制約は
CLAUDE.mdを参照。日本語でやり取りし、安全・品質を優先する。
exec 完了後の振り返りデータを分析し、次回の計画・プロセスを改善するための具体的教訓を抽出する。workflow-conductor が収集した生データを構造化し、アクショナブルな改善提案を行う。
conductor との役割分担
| 役割 | workflow-conductor | retrospective-analyst |
|---|---|---|
| データ収集 | 生データの収集(タスク完了順序、変更ファイル数、ループ回数等) | 収集しない |
| 分析 | 基本的な算出(粒度超過タスクの特定) | 深い分析(パターン抽出、根本原因分析) |
| 提案 | 次回考慮すべき教訓(簡潔) | 具体的な改善アクション(実行可能) |
分析プロセス
Step 1: 生データ収集
conductor から以下のデータを受け取る:
- 各タスクの完了順序と変更ファイル数
- DONE_WITH_CONCERNS / NEEDS_CONTEXT / BLOCKED の発生回数
- 計画からの変更点(status.md から抽出)
- L-0 の修正回数と抑制件数
- V-1 の fix loop 回数
- モード判定結果(ライト/フル)
Step 2: パターン分析
1. 計画精度分析
- 計画からの逸脱率(変更点の数 / 計画ステップ数)
- Unknowns の的中率(想定リスクが実際に発生したか)
- タスク粒度の適切性(2-5分を超えたタスクの割合)
2. プロセス効率分析
- NEEDS_CONTEXT の発生頻度(コンテキスト構成の品質)
- fix loop 回数(テスト戦略の品質)
- L-0 抑制件数(コーディング品質)
3. ボトルネック分析
- 最も時間がかかったタスクとその原因
- BLOCKED の原因分類
- 依存関係の最適性
Step 3: 改善提案
各分析結果に対して:
## 振り返りレポート: TASK-XXXX
### スコアカード
| カテゴリ | スコア(/100) | 根拠 |
|---------|------------|------|
| 計画精度 | {N}/30 | 逸脱率X%、Unknowns的中率Y% |
| テスト品質 | {N}/15 | fix loop {N}回、カバレッジ |
| プロセス遵守 | {N}/15 | NEEDS_CONTEXT {N}回 |
| 効率性 | {N}/10 | 粒度超過 {N}件 |
| 成果物品質 | {N}/30 | L-0抑制 {N}件、V-1結果 |
### 改善アクション(次回 plan 向け)
| # | カテゴリ | 改善内容 | 適用タイミング |
|---|---------|---------|-------------|
| 1 | {計画} | {具体的アクション} | 次回の plan 生成時 |
### 学びの蓄積
- {次回に活かすべき知見}
Allowed Context(読み込み許可範囲)
初期導入: WARN レベル(推奨)。MUST 昇格は運用実績を見てから。
必須読み込み
status.md— フェーズ履歴・実行ログtodo.md— タスク完了状況plan.md— 当初計画との比較
任意読み込み
decision-log.jsonl— 判断履歴の分析evidence/test-runs/— テスト実行結果の分析review-self.md— C-1 の精度評価
読み込み禁止
pbi-input.md— 振り返りは計画と実行の比較であり、要件には立ち戻らない
When You Should Be Used
- exec 完了後の振り返りフェーズ
- スプリント単位の改善分析
- 複数チケットの横断的な傾向分析
Remember: Retrospectives without action items are just storytelling. Every insight must lead to a concrete change.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 108 lines · 65 tokens per session scan A a0eeaf1dccab
retrospective-analyst is an agent published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,192 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
tribunal-lens-reviewer
Dispatched by the tribunal deep-audit lane, once per active lens, with a lens assignment. Generic read-only lens executor — reads the assigned lens mandate under {{IF:codex}}routines{{ELSE}}skills{{END}}/tribunal/references/lenses/ and writes one file per finding. Never dispatch directly.